File size: 8,060 Bytes
3d13ba6
 
 
 
 
 
 
d9ab8fb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3d13ba6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4284c63
3d13ba6
d9ab8fb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3d13ba6
 
d9ab8fb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3d13ba6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d9ab8fb
3d13ba6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
from typing import Dict, Union
from gliner import GLiNER
import gradio as gr

jp_model = GLiNER.from_pretrained("vumichien/ner-jp-gliner")
meal_model = GLiNER.from_pretrained("urchade/gliner_mediumv2.1")


def merge_tokens(entities, text):
    # Remove spaces from the text
    merged_text = text.replace(" ", "")

    updated_entities = []
    for entity in entities:
        # Calculate the new start and end positions
        start = entity['start']
        end = entity['end']

        # Get the text without spaces
        entity_text = entity['text'].replace(" ", "")

        # Find the new start and end in the merged text
        new_start = merged_text.find(entity_text)
        new_end = new_start + len(entity_text)

        # Update the entity with new positions
        updated_entities.append({
            'start': new_start,
            'end': new_end,
            'text': entity_text,
            'label': entity['label'],
            'score': entity['score']
        })

    return updated_entities


examples = [
    [
        "ner_jp",
        "SPRiNGSと最も仲の良いライバルグループ。",
        "その他の組織名, 法人名, 地名, 人名",
        0.3,
        True,
    ],
    [
        "ner_jp",
        "レッドフォックス株式会社は、東京都千代田区に本社を置くITサービス企業である",
        "その他の組織名, 法人名, 地名, 人名",
        0.3,
        False,
    ],
]


def ner(
    text, models:str, labels: str, threshold: float, nested_ner: bool
) -> Dict[str, Union[str, int, float]]:
    labels = labels.split(",")
    if models == "ner_jp":
        model = jp_model
        tokenized_text = " ".join(list(text))
        entities = model.predict_entities(tokenized_text, labels, flat_ner=not nested_ner, threshold=threshold)
        updated_entities = merge_tokens(entities, tokenized_text)
        return {
            "text": text,
            "entities": [
                {
                    "entity": entity["label"],
                    "word": entity["text"],
                    "start": entity["start"],
                    "end": entity["end"],
                    "score": 0,
                }
                for entity in updated_entities
            ],
        }
    else:
        model = meal_model
        return {
            "text": text,
            "entities": [
                {
                    "entity": entity["label"],
                    "word": entity["text"],
                    "start": entity["start"],
                    "end": entity["end"],
                    "score": 0,
                }
                for entity in model.predict_entities(
                    text, labels, flat_ner=not nested_ner, threshold=threshold
                )
            ],
        }


with gr.Blocks(title="GLiNER-M-v2.1") as demo:
    gr.Markdown(
        """
        # GLiNER-base
        GLiNER is a Named Entity Recognition (NER) model capable of identifying any entity type using a bidirectional transformer encoder (BERT-like). It provides a practical alternative to traditional NER models, which are limited to predefined entities, and Large Language Models (LLMs) that, despite their flexibility, are costly and large for resource-constrained scenarios.
        ## Links
        * Model: https://huggingface.co/vumichien/ner-jp-gliner
        * All GLiNER models: https://huggingface.co/models?library=gliner
        * Paper: https://arxiv.org/abs/2311.08526
        * Repository for finetune: https://github.com/vumichien/gliner-medium
        """
    )
    with gr.Accordion("How to run this model locally", open=False):
        gr.Markdown(
            """
            ## Installation
            To use this model, you must install the GLiNER Python library:
            ```
            !pip install gliner
            ```
         
            ## Usage
            Once you've downloaded the GLiNER library, you can import the GLiNER class. You can then load this model using `GLiNER.from_pretrained` and predict entities with `predict_entities`.
            """
        )
        gr.Code(
            '''
from gliner import GLiNER
model = GLiNER.from_pretrained("urchade/gliner_mediumv2.1")
text = """
Cristiano Ronaldo dos Santos Aveiro (Portuguese pronunciation: [kɾiʃˈtjɐnu ʁɔˈnaldu]; born 5 February 1985) is a Portuguese professional footballer who plays as a forward for and captains both Saudi Pro League club Al Nassr and the Portugal national team. Widely regarded as one of the greatest players of all time, Ronaldo has won five Ballon d'Or awards,[note 3] a record three UEFA Men's Player of the Year Awards, and four European Golden Shoes, the most by a European player. He has won 33 trophies in his career, including seven league titles, five UEFA Champions Leagues, the UEFA European Championship and the UEFA Nations League. Ronaldo holds the records for most appearances (183), goals (140) and assists (42) in the Champions League, goals in the European Championship (14), international goals (128) and international appearances (205). He is one of the few players to have made over 1,200 professional career appearances, the most by an outfield player, and has scored over 850 official senior career goals for club and country, making him the top goalscorer of all time.
"""
labels = ["person", "award", "date", "competitions", "teams"]
entities = model.predict_entities(text, labels)
for entity in entities:
    print(entity["text"], "=>", entity["label"])
            ''',
            language="python",
        )
        gr.Code(
            """
Cristiano Ronaldo dos Santos Aveiro => person
5 February 1985 => date
Al Nassr => teams
Portugal national team => teams
Ballon d'Or => award
UEFA Men's Player of the Year Awards => award
European Golden Shoes => award
UEFA Champions Leagues => competitions
UEFA European Championship => competitions
UEFA Nations League => competitions
Champions League => competitions
European Championship => competitions
            """
        )

    input_text = gr.Textbox(
        value=examples[0][0], label="Text input", placeholder="Enter your text here"
    )
    with gr.Row() as row:
        models = gr.Dropdown(
            choices=["ner_meals", "ner_jp"]
            value="ner_jp",
            label="Models",
            placeholder="Enter your test model",
            scale=2,
        )
        labels = gr.Textbox(
            value=examples[0][2],
            label="Labels",
            placeholder="Enter your labels here (comma separated)",
            scale=2,
        )
        threshold = gr.Slider(
            0,
            1,
            value=0.3,
            step=0.01,
            label="Threshold",
            info="Lower the threshold to increase how many entities get predicted.",
            scale=1,
        )
        nested_ner = gr.Checkbox(
            value=examples[0][2],
            label="Nested NER",
            info="Allow for nested NER?",
            scale=0,
        )
    output = gr.HighlightedText(label="Predicted Entities")
    submit_btn = gr.Button("Submit")
    examples = gr.Examples(
        examples,
        fn=ner,
        inputs=[input_text, models, labels, threshold, nested_ner],
        outputs=output,
        cache_examples=True,
    )

    # Submitting
    input_text.submit(
        fn=ner, inputs=[input_text, models, labels, threshold, nested_ner], outputs=output
    )
    models.submit(
        fn=ner, inputs=[input_text, models, labels, threshold, nested_ner], outputs=output
    )
    labels.submit(
        fn=ner, inputs=[input_text, models, labels, threshold, nested_ner], outputs=output
    )
    threshold.release(
        fn=ner, inputs=[input_text, models, labels, threshold, nested_ner], outputs=output
    )
    submit_btn.click(
        fn=ner, inputs=[input_text, models, labels, threshold, nested_ner], outputs=output
    )
    nested_ner.change(
        fn=ner, inputs=[input_text, models, labels, threshold, nested_ner], outputs=output
    )

demo.queue()
demo.launch()